用匹配的键合并行

Question

我有一个具有以下结构的文本文件ID,operator,a,b,c,d,trueWCBP12236,J1,75.7,80.6,65.9,83.2,82.1WCBP12236,J2,76.3,79.6,61.7,81.9,82.1WCBP12236,S1,77.2,81.5,69.4,84.1,82.1WCBP12236,S2,68.0,68.0,53.2,68.5,82.1WCBP12234,J1,63.7,67.7,72.2,71.6,75.3WCBP12234,J2,68.6,68.4,41.4,68.9,75.3WCBP12234,S1,81.8,82.7,67.0,87.5,75.3WCBP12234,S2,66.6,67.9,53.0,70.7,75.3WCBP12238,J1,78.6,79.0,56.2,82.1,84.1WCBP12239,J2,66.6,72.9,79.5,76.6,82.1WCBP12239,S1,86.6,87.8,23.0,23.0,82.1WCBP12239,S2,86.0,86.9,62.3,89.7,82.1WCBP12239,J1,70.9,71.3,66.0,73.7,82.1WCBP12238,J2,75.1,75.2,54.3,76.4,84.1WCBP12238,S1,65.9,66.0,40.2,66.5,84.1WCBP12238,S2,72.7,73.2,52.6,73.9,84.1每个ID数据集都对应一个数据集，操作员会对其进行多次分析。即J1和J2是由操作者J的措施，第一和第二次尝试a，b，c和d使用4个略有不同的算法来测量其真正价值在于所述列中的值true我想做的是创建3个新的文本文件，比较J1vs J2，S1vsS2和J1vs的结果S1。J1vs的示例输出J2：ID,operator,a1,a2,b1,b2,c1,c2,d1,d2,trueWCBP12236,75.7,76.3,80.6,79.6,65.9,61.7,83.2,81.9,82.1WCBP12234,63.7,68.6,67.7,68.4,72.2,41.4,71.6,68.9,75.3其中a1被测量a为J1等另一个例子是S1vs S2：ID,operator,a1,a2,b1,b2,c1,c2,d1,d2,trueWCBP12236,77.2,68.0,81.5,68.0,69.4,53.2,84.1,68.5,82.1WCBP12234,81.8,66.6,82.7,67.9,67.0,53,87.5,70.7,75.3这些ID不会按字母数字顺序排列，也不会为同一ID聚集运算符。我不确定如何最好地完成此任务-使用linux工具或像perl / python这样的脚本语言。我最初使用linux的尝试很快就碰壁了首先找到所有唯一ID（已排序）awk -F, '/^WCBP/ {print $1}' file | uniq | sort -k 1.5n > unique_ids通过这些ID循环和排序J1，J2：foreach i (`more unique_ids`)    grep $i test.txt | egrep 'J[1-2]' | sort -t',' -k2end这给我排序的数据WCBP12234,J1,63.7,67.7,72.2,71.6,75.3WCBP12234,J2,68.6,68.4,41.4,68.9,80.4WCBP12236,J1,75.7,80.6,65.9,83.2,82.1WCBP12236,J2,76.3,79.6,61.7,81.9,82.1WCBP12238,J1,78.6,79.0,56.2,82.1,82.1WCBP12238,J2,75.1,75.2,54.3,76.4,82.1WCBP12239,J1,70.9,71.3,66.0,73.7,75.3WCBP12239,J2,66.6,72.9,79.5,76.6,75.3我不确定如何重新排列这些数据以获得所需的结构。我试图awk在foreach循环中添加一个额外的管道awk 'BEGIN {RS="\n\n"} {print $1, $3,$10,$4,$11,$5,$12,$6,$13,$7}'有任何想法吗？我敢肯定，可以使用awk，以较少麻烦的方式完成此操作，尽管使用适当的脚本语言可能会更好。

Answer 1

您可以使用Perl csv模块Text :: CSV提取字段，然后将它们存储在散列中，其中ID是主键，第二个字段是辅助键，所有字段都存储为值。这样，您可以轻松进行所需的比较。如果要保留行的原始顺序，可以在第一个循环内使用数组。

use strict;

use warnings;

use Text::CSV;

my %data;

my $csv = Text::CSV->new({

            binary => 1,      # safety precaution

            eol    => $/,     # important when using $csv->print()

    });

while ( my $row = $csv->getline(*ARGV) ) {

    my ($id, $J) = @$row;   # first two fields

    $data{$id}{$J} = $row;  # store line

}

Answer 2

我没有像TLP那样使用Text :: CSV。如果需要，但对于此示例，我认为由于字段中没有嵌入的逗号，因此对'，'进行了简单的拆分。另外，列出了两个运算符的真实字段（而不是仅列出1），因为我认为最后一个值的特殊情况会使解决方案复杂化。

#!/usr/bin/perl

use strict;

use warnings;

use List::MoreUtils qw/ mesh /;

my %data;

while (<DATA>) {

    chomp;

    my ($id, $op, @vals) = split /,/;

    $data{$id}{$op} = \@vals;

}

my @ops = ([qw/J1 J2/], [qw/S1 S2/], [qw/J1 S1/]);

for my $id (sort keys %data) {

    for my $comb (@ops) {

        open my $fh, ">>", "@$comb.txt" or die $!;

        my $a1 = $data{$id}{ $comb->[0] };

        my $a2 = $data{$id}{ $comb->[1] };

        print $fh join(",", $id, mesh(@$a1, @$a2)), "\n";

        close $fh or die $!;

    }   

}

__DATA__

WCBP12236,J1,75.7,80.6,65.9,83.2,82.1

WCBP12236,J2,76.3,79.6,61.7,81.9,82.1

WCBP12236,S1,77.2,81.5,69.4,84.1,82.1

WCBP12236,S2,68.0,68.0,53.2,68.5,82.1

WCBP12234,J1,63.7,67.7,72.2,71.6,75.3

WCBP12234,J2,68.6,68.4,41.4,68.9,75.3

WCBP12234,S1,81.8,82.7,67.0,87.5,75.3

WCBP12234,S2,66.6,67.9,53.0,70.7,75.3

WCBP12239,J1,78.6,79.0,56.2,82.1,82.1

WCBP12239,J2,66.6,72.9,79.5,76.6,82.1

WCBP12239,S1,86.6,87.8,23.0,23.0,82.1

WCBP12239,S2,86.0,86.9,62.3,89.7,82.1

WCBP12238,J1,70.9,71.3,66.0,73.7,84.1

WCBP12238,J2,75.1,75.2,54.3,76.4,84.1

WCBP12238,S1,65.9,66.0,40.2,66.5,84.1

WCBP12238,S2,72.7,73.2,52.6,73.9,84.1

产生的输出文件如下

J1 J2.txt

WCBP12234,63.7,68.6,67.7,68.4,72.2,41.4,71.6,68.9,75.3,75.3

WCBP12236,75.7,76.3,80.6,79.6,65.9,61.7,83.2,81.9,82.1,82.1

WCBP12238,70.9,75.1,71.3,75.2,66.0,54.3,73.7,76.4,84.1,84.1

WCBP12239,78.6,66.6,79.0,72.9,56.2,79.5,82.1,76.6,82.1,82.1

S1 S2.txt

WCBP12234,81.8,66.6,82.7,67.9,67.0,53.0,87.5,70.7,75.3,75.3

WCBP12236,77.2,68.0,81.5,68.0,69.4,53.2,84.1,68.5,82.1,82.1

WCBP12238,65.9,72.7,66.0,73.2,40.2,52.6,66.5,73.9,84.1,84.1

WCBP12239,86.6,86.0,87.8,86.9,23.0,62.3,23.0,89.7,82.1,82.1

J1 S1.txt

WCBP12234,63.7,81.8,67.7,82.7,72.2,67.0,71.6,87.5,75.3,75.3

WCBP12236,75.7,77.2,80.6,81.5,65.9,69.4,83.2,84.1,82.1,82.1

WCBP12238,70.9,65.9,71.3,66.0,66.0,40.2,73.7,66.5,84.1,84.1

WCBP12239,78.6,86.6,79.0,87.8,56.2,23.0,82.1,23.0,82.1,82.1

更新：要仅获得1个真值，可以将for循环编写为：

for my $id (sort keys %data) {

    for my $comb (@ops) {

        local $" = '';

        open my $fh, ">>", "@$comb.txt" or die $!;

        my $a1 = $data{$id}{ $comb->[0] };

        my $a2 = $data{$id}{ $comb->[1] };

        pop @$a2;

        my @mesh = grep defined, mesh(@$a1, @$a2);

        print $fh join(",", $id, @mesh), "\n";

        close $fh or die $!;

    }   

}

更新：在grep expr中添加了“定义”以进行测试。因为这是正确的方法（而不是仅测试'$ _'，它可能为0并被grep错误地排除在列表之外）。

Answer 3

Python方式：

import os,sys, re, itertools

info=["WCBP12236,J1,75.7,80.6,65.9,83.2,82.1",

  "WCBP12236,J2,76.3,79.6,61.7,81.9,82.1",

  "WCBP12236,S1,77.2,81.5,69.4,84.1,82.1",

  "WCBP12236,S2,68.0,68.0,53.2,68.5,82.1",

  "WCBP12234,J1,63.7,67.7,72.2,71.6,75.3",

  "WCBP12234,J2,68.6,68.4,41.4,68.9,80.4",

  "WCBP12234,S1,81.8,82.7,67.0,87.5,75.3",

  "WCBP12234,S2,66.6,67.9,53.0,70.7,72.7",

  "WCBP12238,J1,78.6,79.0,56.2,82.1,82.1",

  "WCBP12239,J2,66.6,72.9,79.5,76.6,75.3",

  "WCBP12239,S1,86.6,87.8,23.0,23.0,82.1",

  "WCBP12239,S2,86.0,86.9,62.3,89.7,82.1",

  "WCBP12239,J1,70.9,71.3,66.0,73.7,75.3",

  "WCBP12238,J2,75.1,75.2,54.3,76.4,82.1",

  "WCBP12238,S1,65.9,66.0,40.2,66.5,80.4",

  "WCBP12238,S2,72.7,73.2,52.6,73.9,72.7" ]

def extract_data(operator_1, operator_2):

    operator_index=1

    id_index=0

    data={}

    result=[]

    ret=[]

    for line in info:

        conv_list=line.split(",")

        if len(conv_list) > operator_index and ((operator_1.strip().upper() == conv_list[operator_index].strip().upper()) or (operator_2.strip().upper() == conv_list[operator_index].strip().upper()) ):

            if data.has_key(conv_list[id_index]):

                iters = [iter(conv_list[int(operator_index)+1:]), iter(data[conv_list[id_index]])]

                data[conv_list[id_index]]=list(it.next() for it in itertools.cycle(iters))

                continue

            data[conv_list[id_index]]=conv_list[int(operator_index)+1:]

    return data

ret=extract_data("j1", "s2")

print ret

O / P：

{'WCBP12239'：['70 .9'，'86 .0'，'71 .3'，'86 .9'，'66 .0'，'62 .3'，'73 .7'，'89 .7'，'75 .3'，'82 .1']，'WCBP12238' ：['72.7'，'78.6'，'73.2'，'79.0'，'52.6'，'56.2'，'73.9'，'82.1'，'72.7'，'82.1']，'WCBP12234'：['66.6 '，'63 .7'，'67.9'，'67.7'，'53.0'，'72.2'，'70.7'，'71.6'，'72.7'，'75.3']，'WCBP12236'：['68.0'，'75.7 '，'68 .0'，'80 .6'，'53 .2'，'65 .9'，'68 .5'，'83 .2'，'82 .1'，'82 .1']}