On Mar 2, 2:44 pm, "Shawn Milo" <[EMAIL PROTECTED]> wrote:
(snipped)
> I'm attaching both the Perl and Python versions, and I'm open to
> comments on either. The script reads a file from standard input and
> finds the best record for each unique ID (piid). The best is defined
> as follows: The newest expiration date (field 5) for the record with
> the state (field 1) which matches the desired state (field 6). If
> there is no record matching the desired state, then just take the
> newest expiration date.
>
> Thanks for taking the time to look at these.
>
My attempts:
### Perl ###
#!/usr/bin/perl
use strict;
use warnings;
use List::Util qw/reduce/;
use constant {
STATE => 1,
DATE => 6,
TARGET => 5,
};
sub keep_best {
my ($best, $current) = @_;
if ($current->[STATE] eq $current->[TARGET]) {
if ($best->[STATE] eq $best->[TARGET]) {
if ($current->[DATE] gt $best->[DATE]) {
return 0;
}
} else {
return 0;
}
} elsif (
$best->[STATE] ne $best->[TARGET]
and
$current->[DATE] gt $best->[DATE]) {
return 0;
}
return 1;
}
my %input;
# while uses less memory than for:
# the former is an iterator
while (<>)
{
chomp;
my @results = split(/\t/, $_);
my $key = $results[0];
push @{$input{$key}}, [ @results, $_ ];
}
# while uses less memory than for:
# the former is an iterator
while (my ($key, $aref ) = each %input)
{
my $best = reduce {
keep_best( $a, $b ) ? $a : $b
} @$aref;
print $best->[-1], "\n";
}
### Python (re-working John's code) ###
import sys
def keep_best(best, current):
ACTUAL_STATE = 1
# John had these swapped
DESIRED_STATE = 5
EXPIRY_DATE = 6
keep = True
if current[ACTUAL_STATE] == current[DESIRED_STATE]:
if best[ACTUAL_STATE] == best[DESIRED_STATE]:
if current[EXPIRY_DATE] > best[EXPIRY_DATE]:
keep = False
else:
keep = False
else:
if (best[ACTUAL_STATE] != best[ACTUAL_STATE]
and current[EXPIRY_DATE] > best[EXPIRY_DATE]):
keep = False
return keep
def process_file(opened_file=sys.stdin):
PIID = 0
recs = {}
for line in opened_file:
line = line.rstrip('\n')
row = line.split('\t')
row.append(line)
piid = row[PIID]
if piid not in recs:
recs[piid] = []
recs[piid].append(row)
for piid in recs:
best = reduce(lambda b, c: keep_best(b, c) and b or c,
recs[piid])
print best[-1]
if __name__ == "__main__":
process_file()
# "reduce" seems to be Lispish, Pythonic, and Perlish!
--
Hope this helps,
Steve
--
http://mail.python.org/mailman/listinfo/python-list
