用匹配的键合并行

3回答

红糖糍粑

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}

0 0

SMILET

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/perluse 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,J1,75.7,80.6,65.9,83.2,82.1WCBP12236,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,S2,66.6,67.9,53.0,70.7,75.3WCBP12239,J1,78.6,79.0,56.2,82.1,82.1WCBP12239,J2,66.6,72.9,79.5,76.6,82.1WCBP12239,S1,86.6,87.8,23.0,23.0,82.1WCBP12239,S2,86.0,86.9,62.3,89.7,82.1WCBP12238,J1,70.9,71.3,66.0,73.7,84.1WCBP12238,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产生的输出文件如下J1 J2.txtWCBP12234,63.7,68.6,67.7,68.4,72.2,41.4,71.6,68.9,75.3,75.3WCBP12236,75.7,76.3,80.6,79.6,65.9,61.7,83.2,81.9,82.1,82.1WCBP12238,70.9,75.1,71.3,75.2,66.0,54.3,73.7,76.4,84.1,84.1WCBP12239,78.6,66.6,79.0,72.9,56.2,79.5,82.1,76.6,82.1,82.1S1 S2.txtWCBP12234,81.8,66.6,82.7,67.9,67.0,53.0,87.5,70.7,75.3,75.3WCBP12236,77.2,68.0,81.5,68.0,69.4,53.2,84.1,68.5,82.1,82.1WCBP12238,65.9,72.7,66.0,73.2,40.2,52.6,66.5,73.9,84.1,84.1WCBP12239,86.6,86.0,87.8,86.9,23.0,62.3,23.0,89.7,82.1,82.1J1 S1.txtWCBP12234,63.7,81.8,67.7,82.7,72.2,67.0,71.6,87.5,75.3,75.3WCBP12236,75.7,77.2,80.6,81.5,65.9,69.4,83.2,84.1,82.1,82.1WCBP12238,70.9,65.9,71.3,66.0,66.0,40.2,73.7,66.5,84.1,84.1WCBP12239,78.6,86.6,79.0,87.8,56.2,23.0,82.1,23.0,82.1,82.1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）。

0 0

慕哥6287543

Python方式：import os,sys, re, itertoolsinfo=["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 dataret=extract_data("j1", "s2")print retO / 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']}

0 0