Created
March 2, 2011 03:12
-
-
Save coela/850403 to your computer and use it in GitHub Desktop.
Getting JSON data from Genomes Online Database
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
use 5.12.2; | |
use JSON; | |
use Data::Dumper; | |
use LWP::Simple; | |
my @json_places = ( | |
['Complete' , "http://www.genomesonline.org/complete_published.json"], | |
['Bacteria Ongoing' , "http://www.genomesonline.org/bacterial_ongoing.json"], | |
['Eukaryal Ongoing' , "http://www.genomesonline.org/eukaryal_ongoing.json"], | |
['Archaeal Ongoing' , "http://www.genomesonline.org/archaeal_ongoing.json"], | |
['Metagenome' , "http://www.genomesonline.org/microbial.json"], | |
); | |
my $export; | |
for (@json_places){ | |
my $project_type = $_->[0]; | |
my $url = $_->[1]; | |
my $json = get($url); | |
$json =~ s/, ]/]/g; | |
my $gold = decode_json $json; | |
my %count; | |
for my $record (@{$gold->{records}}){ | |
for my $sc (@{$record->{'SequencingCenters'}}){ | |
$count{$sc->{'Name'}} ++; | |
} | |
$count{'Not Shown'}++ unless @{$record->{'SequencingCenters'}}; | |
} | |
my $project_number = scalar @{$gold->{records}}; | |
for my $sc_name (keys %count){ | |
if ($count{$sc_name}/$project_number <= 0.01){ | |
delete $count{$sc_name}; | |
$count{'Others'}++; | |
} | |
} | |
for my $sc_name (sort { $count{$b} <=> $count{$a} } keys %count){ | |
push @{$export->{$project_type}}, [$sc_name,$count{$sc_name}]; | |
} | |
} | |
say encode_json $export; | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment